Yang You lists you as their PhD student. Claim this profile to confirm it and keep the rest of your record right.
Claim this profileAcademic lineage
View as a treeAdvisors
Works16 from public data
- Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models162
A novel method ZSCL is proposed to prevent zero-shot transfer degradation in the continual learning of vision-language models in both feature and parameter space and a more challenging Multi-domain Task Incremental Learning (MTIL) benchmark to evaluate different methods.
- InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning117
InfoBatch is a novel framework aiming to achieve lossless training acceleration by unbiased dynamic data pruning that randomly prunes a portion of less informative samples based on the loss distribution and rescales the gradients of the remaining samples to approximate the original gradient.
- 15
- MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection14
This work reformulates AIGI detection as a Reference-Comparison problem that verifies consistency with the real-image manifold rather than fitting specific forgery cues, and proposes MIRROR (Manifold Ideal Reference ReconstructOR), a framework that explicitly encodes reality priors using a learnable discrete memory bank.
- DD-Ranking: Rethinking the Evaluation of Dataset Distillation14
DD-Ranking, a unified evaluation framework, along with new general evaluation metrics to uncover the true performance improvements achieved by different methods are proposed, which provide a more comprehensive and fair evaluation standard for future research advancements.
- 5
- ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows2
This work contributes CS-54k, a high-quality corpus of scientific Q&A pairs in computer science, built from 14k CC-licensed papers, and derives two complementary subsets: CS-4k, a carefully curated benchmark for evaluating AI's ability to assist scientific research, and CS-50k, a large-scale training dataset.
- Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection1
V-PVP is proposed, a lightweight readout that replaces only the aggregation layer with two parallel streams over the patch velocity field, restoring the temporal potential of frozen video backbones, restoring their advantage on AIGV detection.
- GlobalForge: Towards Robust AI-Generated Image Detection1
The proposed GlobalForge improves average BAcc on 8 in-the-wild benchmark groups by $\mathbf{5.89\%}$ over the previous state-of-the-art, and is clearly ahead of representative baselines on RealDeg-Bench under both single and compound degradations.
- Boosting LLM via Learning from Data Iteratively and Selectively1
This work proposes to perform instruction tuning by iterative data selection by iteratively updating the complexity score for the top-ranked samples and greedily selecting the ones with the highest complexity-diversity score.
- –
- –
- –
- MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training–
A novel optimizer, MERIT, which leverages the max-norm to calculate the trust ratio to constrain the max attention logit more effectively and further construct element-wise trust ratios to provide more robust update scaling by focusing on local weight structures is proposed.
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.